菜单
Enqueue wiki-worthy content (from a chat turn, spec write, PR merge, learning) for later agent-driven classification + ingest. Agents must justify with --reason.
用 Codex 或 Claude 帮你安装 复制这段 Prompt，粘贴到 Codex、Claude 或其他助手里，让它检查 Skill 页面并帮你完成安装。
基于 SOC 职业分类
| name | Wiki Queue Add |
| description | Enqueue wiki-worthy content (from a chat turn, spec write, PR merge, learning) for later agent-driven classification + ingest. Agents must justify with --reason. |
| version | 1.0.0 |
| category | knowledge |
| skillType | claude-skill |
| assignableRoles | ["orchestrator","team-leader"] |
Enqueue a candidate item for the LLM-wiki. This skill does not write to the vault — it adds the item to a queue. A separate wiki-process-queue run (later, batch or bookkeep-triggered) decides whether the item is actually worth saving and where in the vault it lands.
After a chat turn (yours OR a teammate's), pause briefly and ask:
If YES, call wiki-queue-add. DO NOT call it for:
| Flag | Required | Purpose |
|---|---|---|
--vault <path> | yes | Absolute path to the vault root. |
--content <text> | yes | The text to capture. |
--reason <text> | yes | One sentence: WHY is this wiki-worthy? Audit + helps the processor decide where it goes. |
--source-ref <ref> | yes | Stable reference: chat msg id, slack thread, file path, WI id. |
--source-type <type> | no | Default user_chat. Use slack_message, spec_file, pr_merge, record_learning, task_verified when appropriate. |
--queued-by <sess> | no | Defaults to $CREWLY_SESSION_NAME or crewly-orc. |
A pricing decision the team should remember:
bash execute.sh \
--vault ~/Desktop/projects/crewly-projects/crewly/.crewly/wiki \
--content "Anthropic SMB pilot signed at \$799/month, 12-month commit, 30-day onboarding clause" \
--reason "first paid SMB customer + concrete pricing validation point + new contract pattern" \
--source-ref "slack://D0AC7NF5N7L/1779509999.111"
A learning a worker just surfaced:
bash execute.sh \
--vault ~/.crewly/teams/ad923b66-…/wiki \
--content "Gemini text-embedding-004 returned 404 — deprecated. Falling back to keyword search." \
--reason "infra gotcha — affects every team using vector search; future-me will hit this" \
--source-ref "wi:6cf2d54d-…" \
--source-type record_learning
{
"success": true,
"item": {
"id": "uuid",
"status": "pending",
"queuedAt": "2026-05-22T...",
"vaultPath": "...",
"content": "...",
"reason": "...",
...
}
}
The item sits in the queue until processed. Use wiki-queue-list to see pending items and wiki-process-queue to claim + classify + ingest.
400 reason is required — agents MUST justify wiki-worthiness; refusal protects future-me from low-signal noise400 content/sourceRef empty — every queued item needs identifiable provenance400 vaultPath must be absolute — relative paths are rejected; the vault root is part of the audit trailPlan and create a NESTED team hierarchy (parent coordination team + per-stream child teams) for a complex multi-stream goal. Use INSTEAD of recommend-team/materialize-team when the goal names 2+ parallel work-streams (e.g. frontend + backend + DevOps). Onboarding-only.
Search the live web for a query and return ranked results (title, URL, snippet) as JSON. Works with no API key (DuckDuckGo HTML fallback) and uses the Brave Search API or SerpAPI automatically when BRAVE_API_KEY / SERPAPI_KEY is set. Any agent can call it for research, competitor analysis, market/trend lookups, fact-checking, finding sources to cite, or grounding a non-software goal (marketing, growth, commerce) in real-world information.
Transcribe a local audio (or video) file to text with timestamps using Whisper. Defaults to local whisper.cpp (free, offline, word/segment-level timestamps) and automatically falls back to the OpenAI Whisper API (whisper-1) when the local engine is not installed. Any agent can call it for meetings, podcasts, voice notes, interviews, or video audio tracks.
Accept and take the next available task from the task queue. Use when an agent is idle and ready to pick up the highest-priority unassigned task. For assigning tasks to specific agents, use assign-task instead.
Register the agent as active with the Crewly backend on startup. Use when an agent first launches and needs to join the team and become visible to the orchestrator. For confirming responsiveness after registration, use heartbeat instead.
Analyze git changes and produce a structured code review with automated checks for missing tests, debug statements, potential secrets, large changes, and dependency modifications. Use when reviewing staged changes, unstaged diffs, recent commits, or branch comparisons before submitting a pull request. For task-level quality gates, use check-quality-gates instead.